{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:53:00Z","timestamp":1773510780895,"version":"3.50.1"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T00:00:00Z","timestamp":1744070400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000190","name":"University of Alberta","doi-asserted-by":"crossref","award":["E0162"],"award-info":[{"award-number":["E0162"]}],"id":[{"id":"10.13039\/501100000190","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Dental caries is a major global public health problem, especially among young children. Rapid decay progression often necessitates pulp treatment, making accurate pulp condition assessment crucial. Despite advances in pulp management techniques, diagnostic methods for assessing pulp involvement have not significantly improved. This study aimed to develop a machine learning (ML) model to diagnose pulp involvement using radiographs of carious primary molars. Clinical charts and bitewing radiographs of 900 children treated from 2018-2022 at the University of Alberta dental clinic were reviewed, yielding a sample of 482 teeth. images were preprocessed, standardized, and labeled based on clinical diagnoses. Data were split into training, validation, and test sets, with data augmentation applied to classify 2 categories of outcomes. The YOLOv8m-cls model architecture included convolutional and classification layers, and performance was evaluated using top-1 and top-5 accuracy metrics. The YOLOv8m-cls model achieved a top-1 accuracy of 78.7% for upper primary molars and 87.8% for lower primary molars. Validation datasets showed higher accuracy for lower primary teeth. Performance on new test images demonstrated precision, recall, accuracy, and F1-scores, highlighting the model\u2019s effectiveness in diagnosing pulp involvement, with lower primary molars showing superior results. This study developed a promising CNN model for diagnosing pulp involvement in primary teeth using bitewing radiographs, showing promise for clinical application in pediatric dentistry. Future research should explore whole bitewing images, include clinical variables, and integrate heat maps to enhance the model. This tool could streamline clinical practice, improve informed consent, and assist in dental student training.<\/jats:p>","DOI":"10.1371\/journal.pdig.0000816","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T18:01:23Z","timestamp":1744135283000},"page":"e0000816","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep learning-based assessment of pulp involvement in primary molars using YOLO v8"],"prefix":"10.1371","volume":"4","author":[{"given":"Aydin","family":"Sohrabi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nazila","family":"Ameli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2631-6156","authenticated-orcid":true,"given":"Masoud","family":"Mirimoghaddam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuli","family":"Berlin-Broner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hollis","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2249-5465","authenticated-orcid":true,"given":"Maryam","family":"Amin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,4,8]]},"reference":[{"issue":"7","key":"pdig.0000816.ref001","doi-asserted-by":"crossref","first-page":"887","DOI":"10.14219\/jada.archive.2000.0307","article-title":"The science and practice of caries prevention","volume":"131","author":"JD Featherstone","year":"2000","journal-title":"J Am Dent Assoc"},{"key":"pdig.0000816.ref002","volume-title":"Oral health surveillance report: trends in dental caries and sealants, tooth retention, and edentulism, United States: 1999\u20132004 to 2011\u20132016","author":"M Lin","year":"2019"},{"issue":"1","key":"pdig.0000816.ref003","first-page":"CD003220","article-title":"Pulp treatment for extensive decay in primary teeth","author":"G Nadin","year":"2003","journal-title":"Cochrane Database of Systematic Reviews"},{"issue":"6","key":"pdig.0000816.ref004","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1038\/sj.bdj.2014.201","article-title":"Minimally invasive endodontics: challenging prevailing paradigms","volume":"216","author":"AH Gluskin","year":"2014","journal-title":"Br Dent J"},{"key":"pdig.0000816.ref005","first-page":"399","article-title":"Pulp therapy for primary and immature permanent teeth","author":"Dentistry American Academy of Pediatric","year":"2021","journal-title":"The Reference Manual of Pediatric Dentistry"},{"issue":"5","key":"pdig.0000816.ref006","first-page":"Page range needed","article-title":"A diagnostic insight of dental pulp testing methods in pediatric dentistry","volume":"58","author":"A Igna","year":"2022","journal-title":"Medicina (Kaunas)"},{"issue":"3","key":"pdig.0000816.ref007","first-page":"211","article-title":"Vital pulp therapy with new materials for primary teeth: new directions and Treatment perspectives","volume":"30","author":"AB Fuks","year":"2008","journal-title":"Pediatr Dent"},{"issue":"2","key":"pdig.0000816.ref008","doi-asserted-by":"crossref","first-page":"100081","DOI":"10.1016\/j.dentre.2024.100081","article-title":"A review of advancements of artificial intelligence in dentistry","volume":"4","author":"M Ghaffari","year":"2024","journal-title":"Dentistry Review"},{"issue":"5","key":"pdig.0000816.ref009","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1016\/j.oooo.2023.12.790","article-title":"Applications of artificial intelligence in dentomaxillofacial imaging: a systematic review","volume":"138","author":"S Hartoonian","year":"2024","journal-title":"Oral Surg Oral Med Oral Pathol Oral Radiol"},{"issue":"1","key":"pdig.0000816.ref010","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1186\/s12903-024-04046-7","article-title":"Artificial intelligence for radiographic imaging detection of caries lesions: a systematic review","volume":"24","author":"D Albano","year":"2024","journal-title":"BMC Oral Health"},{"issue":"1","key":"pdig.0000816.ref011","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1093\/dmfr\/twad009","article-title":"Machine learning assessment of dental age classification based on cone-beam CT images: a different approach","volume":"53","author":"OB Dogan","year":"2024","journal-title":"Dentomaxillofac Radiol"},{"issue":"1","key":"pdig.0000816.ref012","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1186\/s12903-024-03928-0","article-title":"Automatic dental age calculation from panoramic radiographs using deep learning: a two-stage approach with object detection and image classification","volume":"24","author":"K Kokomoto","year":"2024","journal-title":"BMC Oral Health"},{"issue":"1","key":"pdig.0000816.ref013","first-page":"22","article-title":"Machine learning assisted 5-part tooth segmentation method for CBCT-based dental age estimation in adults","volume":"42","author":"R Merdietio Boedi","year":"2024","journal-title":"J Forensic Odontostomatol"},{"issue":"9","key":"pdig.0000816.ref014","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.1016\/j.joen.2021.06.003","article-title":"Artificial Intelligence in Endodontics: Current Applications and Future Directions","volume":"47","author":"A Aminoshariae","year":"2021","journal-title":"J Endod"},{"issue":"1","key":"pdig.0000816.ref015","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1186\/s12903-024-04235-4","article-title":"Deep learning for determining the difficulty of endodontic treatment: a pilot study","volume":"24","author":"H Karkehabadi","year":"2024","journal-title":"BMC Oral Health"},{"issue":"1","key":"pdig.0000816.ref016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12065-020-00540-3","article-title":"Convolutional neural networks in medical image understanding: a survey","volume":"15","author":"DR Sarvamangala","year":"2022","journal-title":"Evol Intell"},{"issue":"1","key":"pdig.0000816.ref017","first-page":"442","article-title":"The sensitivity and specificity of YOLO v4 for tooth detection on panoramic radiographs","volume":"16","author":"E Astuti","year":"2023","journal-title":"J Int Dental Med Res"},{"issue":"2","key":"pdig.0000816.ref018","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","volume":"128","author":"R Selvaraju","year":"2020","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"pdig.0000816.ref019","doi-asserted-by":"crossref","first-page":"38","DOI":"10.5051\/jpis.2201060053","article-title":"Determination of the stage and grade of periodontitis according to the current classification of periodontal and peri-implant diseases and conditions (2018) using machine learning algorithms","volume":"53","author":"K Erta\u015f","year":"2023","journal-title":"J Periodontal Implant Sci"},{"issue":"6","key":"pdig.0000816.ref020","doi-asserted-by":"crossref","first-page":"933","DOI":"10.3390\/diagnostics11060933","article-title":"Automatic detection of mandibular fractures in panoramic radiographs using deep learning","volume":"11","author":"D-M Son","year":"2021","journal-title":"Diagnostics (Basel)"},{"issue":"4","key":"pdig.0000816.ref021","doi-asserted-by":"crossref","first-page":"293","DOI":"10.22514\/1053-4625-46.4.6","article-title":"Proposing a CNN Method for primary and permanent tooth detection and enumeration on pediatric dental radiographs","volume":"46","author":"E Kaya","year":"2022","journal-title":"J Clin Pediatr Dent"},{"issue":"6","key":"pdig.0000816.ref022","doi-asserted-by":"crossref","DOI":"10.3390\/jcm9061839","article-title":"Deep learning for automated detection of cyst and tumors of the jaw in panoramic radiographs","volume":"9","author":"H Yang","year":"2020","journal-title":"J Clin Med"},{"issue":"4","key":"pdig.0000816.ref023","doi-asserted-by":"crossref","first-page":"942","DOI":"10.3390\/diagnostics12040942","article-title":"Deep learning based detection tool for impacted mandibular third molar teeth","volume":"12","author":"ME Celik","year":"2022","journal-title":"Diagnostics (Basel)"},{"issue":"7","key":"pdig.0000816.ref024","doi-asserted-by":"crossref","first-page":"677","DOI":"10.3390\/machines11070677","article-title":"YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection","volume":"11","author":"M Hussain","year":"2023","journal-title":"Machines"},{"issue":"1","key":"pdig.0000816.ref025","doi-asserted-by":"crossref","first-page":"20077","DOI":"10.1038\/s41598-023-47460-7","article-title":"Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm","volume":"13","author":"R-Y Ju","year":"2023","journal-title":"Sci Rep"},{"key":"pdig.0000816.ref026","volume-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"C-Y Wang","year":"2023"},{"issue":"Suppl 1","key":"pdig.0000816.ref027","doi-asserted-by":"crossref","first-page":"S47","DOI":"10.1016\/j.jdent.2018.04.022","article-title":"Fuzzy gold standards: Approaches to handling an imperfect reference standard","volume":"74","author":"T Walsh","year":"2018","journal-title":"J Dent"},{"issue":"11","key":"pdig.0000816.ref028","doi-asserted-by":"crossref","first-page":"1227","DOI":"10.1177\/0022034519871884","article-title":"Caries detection with near-infrared transillumination using deep learning","volume":"98","author":"F Casalegno","year":"2019","journal-title":"J Dent Res"},{"issue":"1","key":"pdig.0000816.ref029","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1111\/ipd.13200","article-title":"Deep learning-based detection of irreversible pulpitis in primary molars","volume":"35","author":"T Ma","year":"2025","journal-title":"Int J Paediatr Dent"},{"key":"pdig.0000816.ref030","volume-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"C-Y Wang","year":"2023"},{"key":"pdig.0000816.ref031","doi-asserted-by":"crossref","first-page":"104732","DOI":"10.1016\/j.jdent.2023.104732","article-title":"Prediction of pulp exposure before caries excavation using artificial intelligence: Deep learning-based image data versus standard dental radiographs","volume":"138","author":"S Ramezanzade","year":"2023","journal-title":"J Dent"},{"issue":"4","key":"pdig.0000816.ref032","first-page":"203","article-title":"Measures of diagnostic accuracy: basic definitions","volume":"19","author":"A-M \u0160imundi\u0107","year":"2009","journal-title":"EJIFCC"},{"key":"pdig.0000816.ref033","volume-title":"Diagnostic testing accuracy: Sensitivity, specificity, predictive values and likelihood ratios","author":"J Shreffler","year":"2020"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T18:02:38Z","timestamp":1744135358000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0000816"}},"subtitle":[],"editor":[{"given":"Ismini","family":"Lourentzou","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,8]]},"references-count":33,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0000816","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,8]]}}}